---
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- vision
- generated_from_trainer
datasets:
- arrow
metrics:
- accuracy
model-index:
- name: tcg-magic-classifier
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: acidtib/tcg-magic-cards
      type: arrow
      config: default
      split: validation
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.25452380952380954
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# tcg-magic-classifier

This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the acidtib/tcg-magic-cards dataset.
It achieves the following results on the evaluation set:
- Loss: 7.9836
- Accuracy: 0.2545

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 420
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 8.3148        | 1.0   | 488  | 8.2632          | 0.0055   |
| 8.1958        | 2.0   | 976  | 8.1519          | 0.0598   |
| 8.089         | 3.0   | 1464 | 8.0596          | 0.1567   |
| 8.0208        | 4.0   | 1952 | 8.0033          | 0.2276   |
| 7.983         | 5.0   | 2440 | 7.9836          | 0.2545   |


### Framework versions

- Transformers 4.46.0.dev0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1